Byeonggeun Kim
Senior Applied Scientist at Amazon AGI
Personal email: bungkun1349 at gmail dot com
CV | Google Scholar | LinkedIn | email
Byeonggeun Kim
Senior Applied Scientist at Amazon AGI
Personal email: bungkun1349 at gmail dot com
CV | Google Scholar | LinkedIn | email
Summary: Senior Audio Applied Scientist at Amazon AGI (Artificial General Intelligence) with 8+ years of experience in Generative AI. Core contributor to Amazon Nova 2, architecting the complete end-to-end audio pipeline. Spearheaded audio/music generation initiatives, covering the full stack from audio understanding encoders and neural codecs to their integration into Multimodal LLMs. Currently contributing to TTS advancements for large-scale models. Proven ability to bridge research and product, built on a strong foundation of deploying efficient on-device models at Qualcomm AI Research.
WORK EXPERIENCE
Amazon AGI (Artificial General Intelligence) Feb 2023 - Present, Seattle, WA, United States
Senior Applied Scientist Apr 2025 - Present
Applied Scientist Ⅱ Feb 2023 - Mar 2025
Feb 2023 - Jul 2024 , Toronto, ON, Canada
Qualcomm AI Research Apr 2018 - Jan 2023, Seoul, South Korea
Staff AI Researcher Nov 2022 - Jan 2023
Senior AI Researcher Dec 2019 - Nov 2022
AI Researcher Apr 2018 - Nov 2019
PUBLICATIONS & PATENTS
Please refer to Publications & Patents page.
Honors
Alexa Perceptual Technology Award Q3/Q4 2023, Recognized for contribution to Large Language Models that raise the functional bar. Awarded by Amazon in Feb 2024.
Byeonggeun Kim
Challenge Winner, IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge, DCASE Challenge, 2021 [Results]
Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang
Academic Services
Area Chair: ICASSP (2026)
Session Chair: INTERSPEECH (2022)
Reviewer: INTERSPEECH (2023-2025), ICASSP (2023-2026), CVPR (2024-2026), ICCV (2025), WACV (2025, 2026), ACL (2025), AAAI (2025-2026), EMNLP (2025),
Invited Talk:
Efficient and High Fidelity Text-to-Audio Generation: From Parallel Decoding to Causal Streaming @ Yale University (CS Seminar CPSC 7760), Feb 19, 2026
Autoregressive text-to-audio generation approaches @ Amazon Media & Entertainment ML (+AI) Summit, Sep 30, 2025
EDUCATION
M.S. Feb 2016 - Feb 2018
Korea Advanced Institute of Science and Technology (KAIST)
Electrical Engineering
Dissertion: Knowledge base completion with translation based embeddings and negative sampling method
Advisor: Soo-Young Lee
B.S. Feb 2009 - Feb 2016
Korea Advanced Institute of Science and Technology (KAIST)
Electrical Engineering
Double major in Business
Mandatory Military Service
Sergeant Jun 2010 - Mar 2012
Korea Augmentation To the Unitied States Army (KATUSA)
High School. Mar, 2006 - Feb, 2009